Towards a model-free denoising of underwater optical images

Abstract

A major hindrance to underwater operations using cameras comes from the light absorption and scattering by the marine environment, which limits the visibility distance up to a few meters in coastal waters when using low-end cameras. We propose a complete preprocessing framework able to handle the entire spectrum of noises present in underwater images. We show that most, if not all of this preprocessing can be done with very generic methods that do not need any knowledge of the scene or of the turbidity characteristics of the water, while still remaining coherent with the underwater images formation model.